© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64147
    Prev
    Next
    INDEX
    Explanations

    Q: topics or technical fields

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron responds to formal scientific or technical exposition—especially the abstract‐style sentences and domain-specific terminology found at the start of research papers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inductive
    -0.81
    рила
    -0.75
    Indu
    -0.71
     Böh
    -0.69
    คร
    -0.68
     columnName
    -0.68
     Bür
    -0.68
     jendela
    -0.66
    ственного
    -0.66
    setFrom
    -0.66
    POSITIVE LOGITS
     LB
    0.92
     Bounce
    0.88
     collide
    0.88
     Hair
    0.86
     lattice
    0.85
     SOUTH
    0.83
     Bhat
    0.82
    collide
    0.82
     Ladd
    0.82
     lattices
    0.81
    Activations Density 0.006%

    No Known Activations